Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1186 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.5007. Min Act: -0.1700
Data Index: 8218172 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.4694. Min Act: -0.1700
Data Index: 5783813 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.4069. Min Act: -0.1700
Data Index: 6512609 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.3444. Min Act: -0.1700
Data Index: 6412217 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.3444. Min Act: -0.1700
Data Index: 4654869 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.3132. Min Act: -0.1700
Data Index: 4704394 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2819. Min Act: -0.1700
Data Index: 7318712 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2819. Min Act: -0.1700
Data Index: 5329551 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2819. Min Act: -0.1700
Data Index: 6924448 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2507. Min Act: -0.1700
Data Index: 1690815 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2507. Min Act: -0.1700
Data Index: 8406857 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2507. Min Act: -0.1700
Data Index: 2030718 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2194. Min Act: -0.1700
Data Index: 5987262 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2194. Min Act: -0.1700
Data Index: 3222959 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2194. Min Act: -0.1700
Data Index: 4303595 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.1882. Min Act: -0.1700
Data Index: 2911977 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.2194. Min Act: -0.1700
Data Index: 6840279 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.1882. Min Act: -0.1700
Data Index: 8480612 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.1882. Min Act: -0.1700
Data Index: 5421293 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5007. Min Range: -5.5007
Max Act: 5.1569. Min Act: -0.1700
Data Index: 5249626 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19